Create

Sign in to ReadmeX

or

How we handle your data: Privacy Policy

ReadmeX

Your AI reading companion

What would you like to catch up on?

Pick a briefing, or ask your own question.

Your community and people briefings stay personal to you.

University of Michigan

AI overview

Sign in and the AI will write an overview from our coverage.

Headlines · 4

  1. Auto-Robotist Turns Robot Design Trials into Reusable Skills

    The University of Michigan team behind Auto-Robotist says its open-source system uses large language models to propose robot-body changes, train controllers for candidates, and record simulation results as reusable design knowledge. Reported experiments on seven EvoGym soft-body robotics tasks found better final scores than the standard genetic-algorithm baseline, with the skill library also transferring from a 5×5 grid to a 10×10 design space. The evaluation was limited to simulated EvoGym tasks, so performance on three-dimensional designs and real hardware remains unverified.

    新智元 · 🔥 0
  2. CloudOpsBench 1.0 tests AI agents on real AWS DevOps tasks

    The Decoder reports that CloudOpsBench 1.0 is an open-source benchmark with 45 AWS tasks, created by experienced DevOps engineers to evaluate AI agents on tasks such as repairing services, removing resources, restricting access, and deploying updates. In the reported results, Claude Fable 5.1 solved 60% of tasks and GPT-6 Astra solved 53%, while no model completed every task. The University of Michigan team’s analysis attributes about 80% of failures to scope errors, missed services, or premature stops, and about 20% to incorrect actions.

    The Decoder · 🔥 0
  3. NVIDIA's ASPIRE v1.0 frames robot learning as agentic skill discovery

    Researchers from NVIDIA, the University of Michigan, UIUC, UC Berkeley and Carnegie Mellon released ASPIRE v1.0, an open agentic skill-discovery framework for robot manipulation that treats "training" as iterative skill refinement rather than gradient descent, and a "trained model" as a repository of sensorimotor skills rather than floating weights. The project page says v1.0 can solve a Rubik's Cube and reaches 99% success on 80 LIBERO-Pro Goal, Object, Spatial and Long tasks plus selected Robosuite and BEHAVIOR-1K tasks, all self-reported with no independent reproduction supplied. Simulation workflows ship as agent skills for Claude Code and Codex, NVIDIA-owned material is under Apache 2.0, and the project warns that ASPIRE executes language-model-generated Python and is not a security sandbox.

    GitHub Trending · Python · 🔥 0
  4. Laplace Intelligence uses AI agents to red-team physical systems

    Laplace Intelligence is building automated red-teaming for robots, autonomous vehicles and other physical-AI systems, using AI agents to probe interactive simulations for failure cases. TechCrunch reports that its platform combines real-world-derived environments with generated corner cases, while Laplace says the system has customers including Isuzu and Bot Auto. The company was scheduled to present at TechCrunch Disrupt’s Startup Battlefield 200 on October 13.

    TechCrunch AI · 🔥 0

Experience and discussion from the community

Share my University of Michigan experienceAsk about University of Michigan

Nobody has shared their experience with University of Michigan yet.